© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 14576
    Prev
    Next
    INDEX
    Explanations

    whole followed by collective states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ल
    0.77
    ości
    0.70
     It
    0.66
    ల్‌
    0.64
    літы
    0.63
    ти
    0.63
    话
    0.62
    样的
    0.61
    types
    0.61
    кей
    0.61
    POSITIVE LOGITS
     directeur
    0.73
     femme
    0.70
    ’
    0.70
     besuchen
    0.67
    י
    0.67
     masculino
    0.67
     religioso
    0.67
     forceful
    0.66
     qualific
    0.66
     ouvert
    0.65
    Activations Density 0.003%

    No Known Activations